{"id":"https://openalex.org/W4224925047","doi":"https://doi.org/10.1109/icassp43922.2022.9746818","title":"Training Strategies for Automatic Song Writing: A Unified Framework Perspective","display_name":"Training Strategies for Automatic Song Writing: A Unified Framework Perspective","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224925047","doi":"https://doi.org/10.1109/icassp43922.2022.9746818"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746818","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054269959","display_name":"Tao Qian","orcid":"https://orcid.org/0000-0002-8969-906X"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tao Qian","raw_affiliation_strings":["Renmin University of China,School of Information,P.R.China","School of Information, Renmin University of China, P.R.China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China,School of Information,P.R.China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"School of Information, Renmin University of China, P.R.China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008336983","display_name":"Jiatong Shi","orcid":"https://orcid.org/0000-0002-9050-8304"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute,U.S.A","Language Technologies Institute, Carnegie Mellon University, U.S.A"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute,U.S.A","institution_ids":[]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, U.S.A","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075939587","display_name":"Shuai Guo","orcid":"https://orcid.org/0000-0002-2022-8948"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Guo","raw_affiliation_strings":["Renmin University of China,School of Information,P.R.China","School of Information, Renmin University of China, P.R.China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China,School of Information,P.R.China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"School of Information, Renmin University of China, P.R.China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112896504","display_name":"Peter Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Wu","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute,U.S.A","Language Technologies Institute, Carnegie Mellon University, U.S.A"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute,U.S.A","institution_ids":[]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, U.S.A","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102462376","display_name":"Qin Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":["Renmin University of China,School of Information,P.R.China","School of Information, Renmin University of China, P.R.China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China,School of Information,P.R.China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"School of Information, Renmin University of China, P.R.China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5054269959"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.7366,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.68734257,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4738","last_page":"4742"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.8778928518295288},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7767471671104431},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6009160876274109},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.5749677419662476},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5360809564590454},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5073253512382507},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4846797287464142},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4612167775630951},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.422556072473526},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38843202590942383},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1969112753868103},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.09091633558273315}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.8778928518295288},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7767471671104431},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6009160876274109},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.5749677419662476},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5360809564590454},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5073253512382507},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4846797287464142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4612167775630951},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.422556072473526},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38843202590942383},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1969112753868103},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.09091633558273315},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746818","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6200000047683716,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W116902681","https://openalex.org/W1522301498","https://openalex.org/W2078009352","https://openalex.org/W2546938941","https://openalex.org/W2804809828","https://openalex.org/W2809621972","https://openalex.org/W2911876655","https://openalex.org/W2950547518","https://openalex.org/W2952468927","https://openalex.org/W2952711665","https://openalex.org/W2962699523","https://openalex.org/W2963216553","https://openalex.org/W2963535133","https://openalex.org/W2968379763","https://openalex.org/W2978471471","https://openalex.org/W3034589622","https://openalex.org/W3034999214","https://openalex.org/W3037149862","https://openalex.org/W3092850823","https://openalex.org/W3092879656","https://openalex.org/W3112317145","https://openalex.org/W3125394132","https://openalex.org/W3175663427","https://openalex.org/W4301398814","https://openalex.org/W4385245566","https://openalex.org/W6604828220","https://openalex.org/W6631190155","https://openalex.org/W6729383884","https://openalex.org/W6739901393","https://openalex.org/W6755182157","https://openalex.org/W6755406732","https://openalex.org/W6762242920","https://openalex.org/W6762521896","https://openalex.org/W6769311223","https://openalex.org/W6783972320","https://openalex.org/W6833400836"],"related_works":["https://openalex.org/W2360952181","https://openalex.org/W2118466154","https://openalex.org/W4310670065","https://openalex.org/W634160686","https://openalex.org/W2597614303","https://openalex.org/W3214861561","https://openalex.org/W2389838651","https://openalex.org/W1984378309","https://openalex.org/W2413768264","https://openalex.org/W2363573956"],"abstract_inverted_index":{"Automatic":[0],"song":[1],"writing":[2],"(ASW)":[3],"typically":[4],"involves":[5],"four":[6,39,63,181],"tasks:":[7],"lyric-to-lyric":[8],"generation,":[9,11,13,83],"melody-to-melody":[10],"lyric-to-melody":[12,80],"and":[14,31,57,81,116,131,174],"melody-to-lyric":[15,82],"generation.":[16],"Previous":[17],"works":[18],"have":[19],"mainly":[20],"focused":[21],"on":[22],"individual":[23],"tasks":[24,40,65],"without":[25],"considering":[26],"the":[27,55,71,106,111,128,146,154,167,170,175],"correlation":[28,113],"between":[29,114],"them,":[30],"thus":[32],"a":[33,51,96,132],"unified":[34,52,176],"framework":[35,53],"to":[36,60,100,109,156],"solve":[37],"all":[38,62,180],"has":[41],"not":[42],"yet":[43],"been":[44],"explored.":[45],"In":[46,92],"this":[47,151],"paper,":[48],"we":[49,84,94],"propose":[50],"following":[54],"pre-training":[56,87],"fine-tuning":[58,107],"paradigm":[59],"address":[61],"ASW":[64,158],"with":[66,89,196],"one":[67],"model.":[68],"To":[69,145],"alleviate":[70],"data":[72,78,104],"scarcity":[73],"issue":[74],"of":[75,148,169],"paired":[76,103],"lyric-melody":[77],"for":[79,159],"adopt":[85],"two":[86],"stages":[88],"unpaired":[90],"data.":[91],"addition,":[93],"introduce":[95],"dual":[97,171],"transformation":[98,172],"loss":[99,173],"fully":[101],"utilize":[102],"in":[105,142,162],"stage":[108],"enforce":[110],"weak":[112],"melody":[115],"lyrics.":[117],"We":[118],"also":[119,186],"design":[120],"an":[121],"objective":[122],"music":[123],"generation":[124],"evaluation":[125,192],"metric":[126,193],"involving":[127],"chromatic":[129],"rule":[130],"more":[133],"realistic":[134],"setting,":[135],"which":[136],"removes":[137],"some":[138],"strict":[139],"assumptions":[140],"adopted":[141],"previous":[143],"works.":[144],"best":[147],"our":[149,189],"knowledge,":[150],"work":[152],"is":[153],"first":[155],"explore":[157],"pop":[160],"songs":[161],"Chinese.":[163],"Extensive":[164],"experiments":[165],"demonstrate":[166],"effectiveness":[168],"model":[177],"structure":[178],"encompassing":[179],"tasks.":[182],"The":[183],"experimental":[184],"results":[185],"show":[187],"that":[188],"proposed":[190],"new":[191],"aligns":[194],"better":[195],"subjective":[197],"opinion":[198],"scores":[199],"from":[200],"human":[201],"listeners.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}